b3b5ddb07a
Support I mode images in LoadImageMask.
2024-01-08 17:08:17 -05:00
6a10640f0d
Support properly loading images with mode I.
2024-01-08 03:46:36 -05:00
a7874d1a8b
Add support for the stable diffusion x4 upscaling model.
...
This is an old model.
Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
2024-01-03 03:37:56 -05:00
04b713dda1
Fix VALIDATE_INPUTS getting called multiple times.
...
Allow VALIDATE_INPUTS to only validate specific inputs.
2023-12-29 17:36:40 -05:00
a1e1c69f7d
LoadImage now loads all the frames from animated images as a batch.
2023-12-20 16:39:09 -05:00
2258f85159
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
2023-12-18 03:48:04 -05:00
574363a8a6
Implement Perp-Neg
2023-12-16 00:28:16 +05:30
6761233e9d
Implement Self-Attention Guidance ( #2201 )
...
* First SAG test
* need to put extra options on the model instead of patcher
* no errors and results seem not-broken
* Use @ashen-uncensored formula, which works better!!!
* Fix a crash when using weird resolutions. Remove an unnecessary UNet call
* Improve comments, optimize memory in blur routine
* SAG works with sampler_cfg_function
2023-12-13 15:52:11 -05:00
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
2023-12-08 02:35:45 -05:00
d19de2753e
Merge branch 'fix_folders_handling' of https://github.com/fazo96/ComfyUI
2023-11-29 14:10:30 -05:00
798a34d009
Lower compress level for image preview.
2023-11-28 04:57:59 -05:00
5b37270d3a
Add a lora loader node for models with no CLIP.
2023-11-25 02:26:50 -05:00
42dfae6331
Nodes to properly use the SDV img2vid checkpoint.
...
The img2vid model is conditioned on clip vision output only which means
there's no CLIP model which is why I added a ImageOnlyCheckpointLoader to
load it. Note that the unClipCheckpointLoader can also load it because it
also has a CLIP_VISION output.
SDV_img2vid_Conditioning is the node used to pass the right conditioning
to the img2vid model.
VideoLinearCFGGuidance applies a linearly decreasing CFG scale to each
video frame from the cfg set in the sampler node to min_cfg.
SDV_img2vid_Conditioning can be found in conditioning->video_models
ImageOnlyCheckpointLoader can be found in loaders->video_models
VideoLinearCFGGuidance can be found in sampling->video_models
2023-11-23 19:48:49 -05:00
1964bf1e78
fix: folder handling issues
2023-11-23 22:24:58 +01:00
cd4fc77d5f
Add taesd and taesdxl to VAELoader node.
...
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
2023-11-21 12:54:19 -05:00
8a451234b3
Add ImageCrop node.
2023-11-18 04:44:17 -05:00
bd07ad1861
Add PatchModelAddDownscale (Kohya Deep Shrink) node.
...
By adding a downscale to the unet in the first timesteps this node lets
you generate images at higher resolutions with less consistency issues.
2023-11-16 13:25:46 -05:00
dcec1047e6
Invert the start and end percentages in the code.
...
This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.
percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.
Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.
2023-11-16 04:23:44 -05:00
ca71e542d2
Lower cfg step to 0.1 in sampler nodes.
2023-11-09 17:35:17 -05:00
844dbf97a7
Add: advanced->model->ModelSamplingDiscrete node.
...
This allows changing the sampling parameters of the model (eps or vpred)
or set the model to use zsnr.
2023-11-07 03:28:53 -05:00
1443caf373
HyperTile node, can be found in: _for_testing->HyperTile
2023-10-21 05:16:38 -04:00
d44a2de49f
Make VAE code closer to sgm.
2023-10-17 15:18:51 -04:00
7e09e889e3
Make clear that the old CheckpointLoader is deprecated.
2023-10-15 02:22:22 -04:00
20d3852aa1
Pull some small changes from the other repo.
2023-10-11 20:38:48 -04:00
9212bea87c
Change a few things in #1578 .
2023-10-04 15:43:41 -04:00
ece69bf28c
Change channel type to MASK (reduced redundancy, increased usability)
2023-10-04 19:04:52 +02:00
d06cd2805d
Added support for Porter-Duff image compositing
2023-10-04 19:04:48 +02:00
ec454c771b
Refactor with code from comment of #1588
2023-10-02 17:26:59 -04:00
1adcc4c3a2
Add a SamplerCustom Node.
...
This node takes a list of sigmas and a sampler object as input.
This lets people easily implement custom schedulers and samplers as nodes.
More nodes will be added to it in the future.
2023-09-27 22:21:18 -04:00
bf3fc2f1b7
Refactor sampling related code.
2023-09-27 16:45:22 -04:00
9546a798fb
Make LoadImage and LoadImageMask return masks in batch format.
2023-09-26 02:56:40 -04:00
ba7dfd60f2
Merge branch 'proportional-scale' of https://github.com/jn-jairo/ComfyUI
2023-09-25 12:39:53 -04:00
2381d36e6d
1024 wasn't enough.
2023-09-25 01:46:44 -04:00
42f6d1ebe2
Increase maximum batch sizes of empty image nodes.
2023-09-25 01:22:37 -04:00
77c124c5a1
Fix typo.
2023-09-24 13:27:57 -04:00
593b7069e7
Proportional scale latent and image
2023-09-24 12:08:54 -03:00
fd93c759e2
Implement FreeU: Free Lunch in Diffusion U-Net node.
...
_for_testing->FreeU
2023-09-23 00:56:09 -04:00
422d16c027
Add some nodes to add, subtract and multiply latents.
2023-09-21 22:23:01 -04:00
1122df1a20
Increase range of lora strengths.
2023-09-20 17:58:54 -04:00
2b6b178173
Added support for lanczos scaling
2023-09-19 10:40:38 +02:00
0109431626
Lower the minimum resolution of EmptyLatentImage.
2023-09-18 16:20:03 -04:00
db63aa7e53
Nodes can now control the rounding in the UI.
2023-09-17 12:49:06 -04:00
f88f7f413a
Add a ConditioningSetAreaPercentage node.
2023-09-06 03:28:27 -04:00
36ea8784a8
Only return tuple of 3 args in CheckpointLoaderSimple.
2023-09-02 03:34:57 -04:00
57beace324
Fix VAEDecodeTiled minimum.
2023-08-31 14:26:16 -04:00
7e941f9f24
Clean up DiffusersLoader node.
2023-08-30 12:57:07 -04:00
8ddd081b09
Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled.
2023-08-29 01:51:35 -04:00
d86b222fe9
Reduce min tile size for encode
2023-08-28 22:39:09 +05:30
9196588088
Make tile size in Tiled VAE encode/decode user configurable
2023-08-28 19:57:22 +05:30
c77f02e1c6
Move controlnet code to comfy/controlnet.py
2023-08-25 17:33:04 -04:00
d7b3b0f8c1
Don't hardcode node names for image upload widget.
2023-08-22 19:41:49 -04:00
9b1d5a587c
Allow loading js extensions without copying to /web folder
2023-08-20 19:55:48 +01:00
27b87c25a1
Add an EmptyImage node.
...
TODO: implement color picker in the frontend.
2023-08-15 17:53:10 -04:00
e7d88855f4
Add node to batch images together.
2023-08-14 20:23:38 -04:00
9cc12c833d
CLIPVisionEncode can now encode multiple images.
2023-08-14 16:54:05 -04:00
fa962e86c1
Make LatentBlend more consistent with other nodes.
2023-08-04 02:51:28 -04:00
d712193885
Add LatentBlend node, allowing for blending between two Latent inputs.
2023-08-01 01:23:14 -05:00
3dcad78fe1
SaveLatent reports its outputs so they are visible to API
2023-07-30 16:36:55 -05:00
1141029a4a
Add --disable-metadata argument to disable saving metadata in files.
2023-07-28 12:31:41 -04:00
5f75d784a1
Start is now 0.0 and end is now 1.0 for the timestep ranges.
2023-07-24 18:38:17 -04:00
7ff14b62f8
ControlNetApplyAdvanced can now define when controlnet gets applied.
2023-07-24 17:50:49 -04:00
d191c4f9ed
Add a ControlNetApplyAdvanced node.
...
The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.
2023-07-24 13:35:20 -04:00
0240946ecf
Add a way to set which range of timesteps the cond gets applied to.
2023-07-24 09:25:02 -04:00
a8f3bbc35d
Patch del self.loaded_lora to prevent error with persistent lora_name swapping
2023-07-15 17:11:12 -07:00
eed3042830
Move conditioning concat node to conditioning section.
2023-07-13 21:44:56 -04:00
bdba394290
Add a canny preprocessor node.
2023-07-13 13:26:48 -04:00
3bc8be33e4
Don't let custom nodes overwrite base nodes.
2023-07-13 12:56:38 -04:00
f4b9390623
Add a random string to the temp prefix for PreviewImage.
2023-07-11 17:35:55 -04:00
ccb1b25908
Add a conditioning concat node.
2023-07-05 17:40:22 -04:00
af7a49916b
Support loading unet files in diffusers format.
2023-07-05 17:38:59 -04:00
3a09fac835
ConditioningAverage now also averages the pooled output.
2023-07-03 21:44:37 -04:00
d94ddd8548
Add text encode nodes to control the extra parameters in SDXL.
2023-07-03 19:11:36 -04:00
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
2d880fec3a
Add a node to zero out the cond to advanced/conditioning
...
The stability streamlit example passes a zero cond as the negative input
so using this for the negative input makes outputs match the streamlit.
2023-06-27 23:30:52 -04:00
9b93b920be
Add CheckpointSave node to save checkpoints.
...
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.
Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32
Anything that patches the model weights like merging or loras will be
saved.
The output directory is currently set to: output/checkpoints but that might
change in the future.
2023-06-26 12:22:27 -04:00
4eab00e14b
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
cef6aa62b2
Add support for TAESD decoder for SDXL.
2023-06-25 02:38:14 -04:00
20f579d91d
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2023-06-25 01:40:38 -04:00
05676942b7
Add some more transformer hooks and move tomesd to comfy_extras.
...
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2023-06-24 03:30:22 -04:00
8607c2d42d
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
bf3f271775
Add some nodes for basic model merging.
2023-06-20 19:17:03 -04:00
8c9c94b5f3
Add bicubic upscale method.
2023-06-17 01:54:33 -04:00
67833c83d8
Add ImageScaleBy node.
2023-06-12 01:14:04 -04:00
c64ca8c0b2
Refactor unCLIP noise augment out of samplers.py
2023-06-11 04:01:18 -04:00
a3a713b6c5
Refactor previews into one command line argument.
...
Clean up a few things.
2023-06-06 02:13:05 -04:00
8b4a6c19c2
Fix
2023-06-05 19:00:51 -05:00
3e17971acb
preview method autodetection
2023-06-05 18:59:10 -05:00
d5a28fadaa
Add latent2rgb preview
2023-06-05 18:39:56 -05:00
70d72c4336
Slightly less vibrant sample
2023-06-05 15:26:56 -05:00
48f7ec750c
Make previews into cli option
2023-06-05 13:19:02 -05:00
f326a0a468
Make new LATENT_PREVIEWER type for declaring KSampler preview methods
2023-06-05 09:20:20 -05:00
b4f434ee66
Preview sampled images with TAESD
2023-06-05 09:20:17 -05:00
0fc483dcfd
Refactor diffusers model convert code to be able to reuse it.
2023-05-28 01:55:40 -04:00
4d1ed829d9
Don't load some model types if weight is zero
2023-05-26 19:33:30 -05:00
c00bb1a0b7
Add a latent upscale by node.
2023-05-23 12:53:38 -04:00
34887b8885
Add experimental bislerp algorithm for latent upscaling.
...
It's like bilinear but with slerp.
2023-05-23 03:12:56 -04:00
6cc450579b
Auto transpose images from exif data.
2023-05-22 00:22:24 -04:00
8bbd9815a9
Support loading fp16 latent files.
2023-05-19 02:15:32 -04:00
62a371e12b
Load workflow from latent file.
2023-05-18 02:41:21 -04:00
comfyanonymous
Hari
Rafie Walker
Enrico Fasoli
MoonRide303
Jairo Correa
BVH
pythongosssss
FuamiCake
ComfyUI-Community
space-nuko